Thanks for that paper. It forced me to remember (and look up) the discussion
in Pearl's book ("Causality" 2000) about the Markov assumption and latent
structure reduction. Part of my reaction to John's statement about trying to
find a time series that cannot be generated by a sequential machine was a
result of Pearl's discussion. The question I'm now worried about is the
facility/frequency with which cyclic graphs can be "simulated" by DAGs (which
is why I implied that everywhere we think there might be a convergence to
something "real" would require a monotonic parameter).
On 12/31/18 12:35 PM, Frank Wimberly wrote:
> Try this link. Now I remember that Thomas Richardson first described the
> algorithm and Danks and I implemented it.
>
> http://scholar.google.com/scholar_url?url=https://arxiv.org/pdf/1302.3599&hl=en&sa=X&scisig=AAGBfm23iOsgxDPx5eHVIU1aXYbP1yc_ZA&nossl=1&oi=scholarr
--
☣ uǝlƃ
============================================================
FRIAM Applied Complexity Group listserv
Meets Fridays 9a-11:30 at cafe at St. John's College
to unsubscribe http://redfish.com/mailman/listinfo/friam_redfish.com
archives back to 2003: http://friam.471366.n2.nabble.com/
FRIAM-COMIC http://friam-comic.blogspot.com/ by Dr. Strangelove
